xAgent is a mobile-first, multi-agent AI system powered by LLMs, featuring real-time chat, coding, and finance built with LangGraph workflows and MCP.
<h1 align="center"> xAgent </h1>
<div align="center">
<img alt="anshRS-xAgent-logo" height="200px" src="/assets/logo.png">
</div>
<p align="center">
Extensible Multitasking Agentic System
</p>
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Introduction](#introduction)
- [Features](#features)
- [Tech Stack](#tech-stack)
- [Architecture](#architecture)
- [Installation](#installation)
- [Prerequisites](#prerequisites)
- [Backend Setup](#backend-setup)
- [Frontend Setup](#frontend-setup)
- [Project Preview](#project-preview)
- [Support](#support)
## Introduction
xAgent is a modular, real-time, intelligent multi-agent mobile application that leverages state-of-the-art language models and clean architecture principles to help users perform tasks across domains like chat, finance, coding, and emailing. The system uses WebSocket communication, LangGraph workflows, and the MCP (Model Context Protocol) design pattern for scalable agent interactions.
## Features
- Secure authentication with JWT
- Profile management with protected routes
- Realtime Chat Agent for general-purpose conversations
- Coding Agent for code generation, debugging, and explanation
- Finance Agent for applying stock strategies and financial analysis
- WebSocket-based real-time communication between agents and backend
- MCP (Model Context Protocol) architecture for modular agent design
- LangGraph based workflow orchestration for stateful task execution
- Clean Architecture and SOLID principles in Flutter frontend
- LLM-powered intelligence using Gemini and LLaMA models
## Tech Stack
| Frontend | Backend | Others |
| ------------------ | ---------- | ------------------|
| `Dart` | `Python` | `Git` |
| `Flutter` | `FastAPI` | `Ollama` |
| `Bloc` | `Supabase` | `Meta Llama` |
| `GetIt` | `LangChain` | `Gemini` |
| `fpDarGoogle's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.